US20050240424A1

Movatterモバイル変換

Info

Publication number: US20050240424A1
Application number: US10/833,444
Authority: US
Inventors: Xiaofan Lin; Steven Simske
Original assignee: Individual
Current assignee: Hewlett Packard Development Co LP
Priority date: 2004-04-27
Filing date: 2004-04-27
Publication date: 2005-10-27

Abstract

A system and method for attribute extraction within a call handling system is disclosed. The method discloses: initiating a dialog between a contact and a call handling system; waiting for a first length of the dialog; assigning the contact to a first attribute category by processing the first length of the dialog using a first instance of a first classifier; waiting for a second length of the dialog; and assigning the contact to a second attribute category by processing the second length of the dialog using a first instance of a second classifier trained to categorize dialogs assigned only to the first attribute category. The system discloses means and mediums for practicing the method.

Description

CROSS-REFERENCE TO RELATED OR CO-PENDING APPLICATIONS

This application relates to co-pending U.S. patent application Ser. No. 10/769240, entitled “System And Method For Language Variation Guided Operator Selection,” filed on Jan. 30, 2004, by Lin et al. This related application is commonly assigned to Hewlett-Packard Development Co. of Houston, Tex.

BACKGROUND OF THE INVENTION

1. Field of the Invention

The present invention relates generally to systems and methods for call handling, and more particularly to for hierarchical attribute extraction within a call handling system.

2. Discussion of Background Art

Automated call handling systems, such as Interactive Voice Response (IVR) systems, using Automatic Speech Recognition (ASR) and Text-to-speech (TTS) software are increasingly important tools for providing information and services to contacts, such as customers, in a more cost efficient manner. IVR systems are typically hosted by call centers that enable contacts to interact with corporate databases and services over a telephone using a combination of voice speech signals and telephone button presses. IVR systems are particularly cost effective when a large number of contacts require data or services that are very similar in nature, such as banking account checking, ticket reservations, etc., and thus can be handled in an automated manner often providing a substantial cost savings due to a need for fewer human operators.

Automated call handling systems often require knowledge of one or more contact attributes in order to most efficiently and effectively provide service to the contact. Such attributes may include the contact's gender, language, accent, dialect, age, and identity. For example, contact gender information may be needed for adaptive advertisements while the contact's accent information may be needed for possible routing to a customer service representative (i.e. operator).

However, extracting such attributes (i.e. metadata) from the contact's speech signals or textual messages is typically a complex and time consuming process. Current methods involve laboriously examining the contact's speech signals and textual messages in order to try and determine each of the contact's attributes. Such systems tend to be slow and have varying accuracy.

In response to the concerns discussed above, what is needed is a system and method for call handling that overcomes the problems of the prior art.

SUMMARY OF THE INVENTION

The present invention is a system and method for hierarchical attribute extraction within a call handling system. The method of the present invention includes the elements of: initiating a dialog between a contact and a call handling system; waiting for a first length of the dialog; assigning the contact to a first attribute category by processing the first length of the dialog using a first instance of a first classifier; waiting for a second length of the dialog; and assigning the contact to a second attribute category by processing the second length of the dialog using a first instance of a second classifier trained to categorize dialogs assigned only to the first attribute category. The system of the present invention includes all means and mediums for practicing the method.

These and other aspects of the invention will be recognized by those skilled in the art upon review of the detailed description, drawings, and claims set forth below.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a dataflow diagram of one embodiment of a system for hierarchical attribute extraction within a call handling system;

FIG. 2 is a Venn diagram of an exemplary set of clustering characteristics;

FIG. 3 is a Venn diagram of an exemplary set of ground-truth training data;

FIG. 4 is a root flowchart of one embodiment of a method for hierarchical attribute extraction within a call handling system; and

FIG. 5 is a flowchart of one embodiment of a method for hierarchical attribute extraction within a call handling system.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT

The present invention discloses a system and method for hierarchically extracting a set of contact attributes from a contact's speech signals or textual messages, thereby taking advantage of synergies between multiple contact attribute classifications. Such hierarchical extraction improves a call handling system's speed and efficiency since downstream attribute classifiers only need process a sub-portion of the contact's speech signal or textual messages. Speed and efficiency are further improved by varying the length of the speech signal or text message required by a set of classifiers that identify the contact's attributes.

FIG. 1 is a dataflow diagram of one embodiment of asystem100 for hierarchical attribute extraction within acall handling system102. Thecall handling system102 of the present invention preferably provides some type of voice interactive information management service to a set of contacts. Anticipated information services include those associated with customer response centers, enterprise help desks, business generation and marketing functions, competitive intelligence methods, as well as many others. Contacts may be customers, employees, or any party in need of the call center's services.

To begin, acontact104 enters into a dialog with thecall handling system102. While the dialog typically begins once adialog manager106 connects thecontact104 to an Interactive Voice Response (IVR)module108 through adialog router110, alternative dialogs could route thecontact104 directly or eventually to ahuman operator112. TheIVR module108 provides an automated interface between the contact's104 speech signals and the system's102 overall functionality. To support such an interface with thecontact104, theIVR module108 may include a Text-To-Speech (TTS) translator, Natural Language Processing (NLP) algorithms, Automated Speech Recognition (ASR), and various other dialog interpretation (e.g. a Voice-XML interpreter) tools. As part of the dialog, theIVR module108 receives information requests and responses from thecontact104 that are then processed and stored in accordance with the call handling system's102 functionality in acontact database114. Thesystem102 may also receive textual messages from thecontact104 during the dialog.

Indentify Contact Attributes for Classification

Thedialog manager106 retrieves a request to identify a predetermined set of contact attributes with respect to thecontact104. Such requested contact attributes may include the contact's gender, language, accent, dialect, age, or identity, as is dictated by the system's102 functionality.

The request is preferably stored in memory prior to initiation of the dialog by thecontact104 due to a need to train a set of attribute classifiers on ground-truth data before performing hierarchical attribute extraction. Hierarchical attribute extraction is discussed in more detail below. In an alternate embodiment, the request can be generated in real-time as thesystem102 interacts with the contact104 (i.e. automatically generated as part of the dialog hosted by theIVR module108 or based on inputs received from the operator112).

Classifier Selection

A set of

classifiers

116,118, and120 required to extract the contact attributes from the contact's speech signals and textual messages are selected by thedialog manager106.

Each of the

classifiers

116,118, and120 can be labeled either according to the set of categories (i.e. gender, accent, age, etc.) to which the classifier assigns the contact's104 input data (i.e. speech signals and textual messages), or according to how the classifier operates (i.e. acoustic classifier, keyword classifier, business relevance classifier, and etc.).

Such classifier labels overlap, so that a gender classifier may employ both acoustic and keyword techniques and a keyword classifier may be used for both gender and accent classification. In the present invention, however, the classifiers are preferably labeled and hierarchically sequenced according to the set of categories to which the classifier assigns the contact's104 input data. Those skilled in the art however will recognize that in alternate embodiments the hierarchical sequencing can be based on classifier operation instead.

Hierarchically Sequence Classifiers

How the

classifiers

116,118, and120 are finally sequenced depends in part upon a set of characteristics used to evaluate each of the classifiers and in part based on how classifier sequencing affects theoverall system102 performance. The classifiers'116,118, and120 individual characteristics and the system's102 overall performance are estimated using a set of ground-truth data. The ground-truth data preferably includes a statistically significant set of pre-recorded speech signals and text messages authored by a predetermined set of contacts having known attributes (i.e. gender, age, accent, etc.).

Theclassifier sequencer122 sends the ground-truth data to each classifier for classification. Theclassifier sequencer122 receives a set of classification data-points back from each classifier (e.g. a gender classifier and an accent classifier).

Each portion of the sequencing process is now discussed in more detail.

Classifier Clustering Characteristics

FIG. 2 is a Venn diagram of an exemplary set ofclustering characteristics200 for a set of classifiers that have processed a predetermined set of ground-truth data, and is used to help illustrate the discussion that follows.

Theclassifier sequencer122 calculates an “inter-class distance” between all data-points known (via the ground-truth data) to be within a first attribute category (e.g. “Male Gender”202, or “British Accent”204) and all data-point known to be within a second attribute category (i.e. “Female Gender”206, or “American Accent”208). Those skilled in the art recognize that in other embodiments of the present invention, each classifier may classify the data-points into more that two categories (e.g. “American Accent”, “British Accent”, “Asian Accent”, and so on).

For example, using data-

points

210, and212 shown inFIG. 2, the “inter-class distance” between the “Male Gender”202 category and the “Female Gender”206 category would be equal to a distance betweendp1210 anddp2212. Theclassifier sequencer122 averages all of these inter-class distances over the entire set of classification data-points.

Theclassifier sequencer122 calculates an “intra-class distance” between all data-points known (via the ground-truth data) to be within a first attribute category (e.g. “Male Gender”202, “British Accent”204, “Female Gender”206, or “American Accent”208).

For example, using data-

points

210, and214 shown inFIG. 2, the “intra-class distance” for the “Male Gender”202 category would be equal to a distance betweendp1210 anddp3214. Theclassifier sequencer122 averages all of these intra-class distances over the entire set of classification data-points.

Next, theclassifier sequencer122 defines a clustering characteristic for each classifier based on a ratio between the average “inter-class distance” and average “intra-class distance”. Theclassifier sequencer122 sequences the

classifiers

116,118, and120 based on this ratio. Preferably, the ratio is equal to the average inter-class distance divided by the average intra-class distance, such that those classifiers generating tighter intra-class clusters, as compared to their inter-class clusters will have a higher ratio that those classifiers having looser clustering characteristics.

In the exemplary data ofFIG. 2, a gender classifier categorized the data-points into non-overlapping “Male Gender”202 and “Female Gender”206 categories, whereas an accent classifier categorized the data-points into very overlapping “British Accent”204 and “American Accent”208 categories. In such an example, which has also been observed during a reduction to practice, gender classification is preferably done before accent classification. Those skilled in the art however will know that actual clustering characteristics may vary with each application of the present invention, and the characteristics inFIG. 2 are only for the purposes of illustrating how the present invention operates.

Classifier Accuracy Characteristics

Classifier accuracy characteristics are covariant with yet distinct from classifier clustering characteristics. As such, the accuracy characteristics mostly provide just a different perspective on classifier performance.

Thus, theclassifier sequencer122 calculates an accuracy rate, which is the ratio between a number of the classification data-points that fall within a correct classifier category, according to the ground-truth data, and a total number of the classification data-points.

Theclassifier sequencer122 sequences the

classifiers

116,118, and120 based on this accuracy rate. Preferably, the classifier having a highest accuracy rate is first in the sequence, followed by the less accurate classifiers.

Classifier Saturation Characteristics

Theclassifier sequencer122 sends a set of ground-truth data, having a predetermined speech signal or textual length, to each classifier for classification. Theclassifier sequencer122 receives a set of classification data-points back from each classifier for each of the predetermined speech signal or textual lengths. Theclassifier sequencer122 calculates an accuracy rate, which is the ratio between a number of the classification data-points that fall within a correct classifier category, according to the ground-truth data, and a total number of the classification data-points, for each of the predetermined speech signal or textual lengths.

Then, theclassifier sequencer122 compares the accuracy rate to the predetermined speech signal or textual lengths, resulting in a classifier saturation curve for each classifier. Theclassifier sequencer122 sequences the

classifiers

116,118, and120 according to how quickly each classifier reaches a predetermined point in that classifier's saturation curve. Preferably, the classifier requiring a shortest speech signal or textual lengths to reach the predetermined saturation point is first in the sequence, followed by the slower classifiers.

For example, if gender classification requires only a one second speech signal to accurately classify the contact's104 gender, whereas accent classification requires about a 30 to 40 second speech signal before accurately classifying the contact's104 accent, then theclassifier sequencer122 would sequence gender classification before accent classification. Such ordering also permits thesystem102 to more quickly use information about the contact's104 gender during the course of the dialog, while waiting for the contact's104 accent to be accurately identified. This is analogous to “a short job first” dispatch strategy used in batch job system.

Other Classifier Characteristics

Theclassifier sequencer122 can also be programmed to characterize the

classifiers

116,118, and120 according to many other metrics, including: classifier resource requirements (i.e. computer hardware required to effect the classifier's functionality), and cost (i.e. if a royalty or licensing fee must be paid to effect the classifier). Theclassifier sequencer122 can also be programmed to calculate a composite classifier characteristic equal to a weighted sum of a predetermined set of individually calculated classifier characteristics.

Theclassifier sequencer122 stores the classifier characterization data in aclassifier database124.

Classifier Sequencing

Theclassifier sequencer122 select a sequence for executing each of the

classifiers

116,118, and120 based on a weighted combination of each of the classifier characteristics. Thus downstream contact attribute classifications only search in a subspace defined by upstream contact attribute classifications. For example, if classifier accuracy is weighted most highly and gender classification has a higher accuracy than accent classification, thedialog manager106 will effect gender classification on the dialog with thecontact104 first, after which, thedialog manager106 will effect accent classification using an accent model based on the gender identified for thecontact104, as is discussed in more detail below.

Next, theclassifier sequencer122 further optimizes the sequence for executing each of the

classifiers

116,118, and120 using a genetic algorithm. Genetic algorithms work by generating a pool of sequences through reproduction (duplicating the old sequence), mutation (random changing part of the old sequence), and crossover (taking parts from two old sequences and forming a new sequence). Before doing reproduction, a metric for each sequence is first evaluated. The better the metric is, the bigger a chance the sequence will participate in the reproduction. In this way, the pool of sequences will be improved generation after generation, so that a best sequence can be selected in a final generation.

Optimize Dialog Length Processed by Each Classifier

Thedialog manager106 selects a dialog length (t_a, t_b, and t_n, respectively) for each of the

classifiers

116,118, and120. The dialog length is the length of the dialog between thecontact104 and thesystem102 which a classifier is given in order to classify a selectedcontact104 attribute. In general, the longer the dialog length used then the higher the classifier's accuracy. However, as discussed above each classifier has a saturation characteristic so that longer dialog lengths yield less proportional improvements in accuracy, so a reasonable tradeoff is made, preferably using a cost function of the form:
C(t_a, t_b, . . . , t_n)=w_a*t_a+w_b*t_b+ . . . +w_n*t_n−(1−E_a(t_a))*(1−E_b(t_b))* . . . *(1−E_n(t_n)),
where t_a, t_b, and t_ncorrespond to the dialog lengths fed to each

classifier

116,118, and120, w_a, w_b, and w_nare classifier weights, and E_a, E_b, and E_nare each classifier's respective error probabilities as a function of the dialog lengths.

The weighted summation part (i.e. w_a*t_a+w_b*t_b+ . . . +w_n*t_n) reflects a penalty for processing longer utterances, and the last items (i.e. (1−E_a(t_a))*(1−E_b(t_b))* . . . *(1−E_n(t_n))) calculate a probability that each of the contact attribute classifications are done correctly, which is the product of the error probabilities of the individual classifiers. The weights (i.e. w_a, w_b, and w_n) can be decided bysystem102 requirements. For example, if thesystem102 expeditiously requires the contact's104 gender, the gender classifier's weight should be larger, relative to the other classifier's weights.

Thedialog manager106 selects the dialog lengths for each of the

classifiers

116,118, and120 using numerical optimization methods that minimize the cost function. For example: first initialize (t_a, t_b, and t_n) and calculate a first cost C; next modify t_aby a small amount δ and calculate a second cost C′. If the second cost C′ is smaller than the first cost C′ keep the δ change to t_aotherwise change t_aby −δ. If C′ and C are equivalent, keep t_aunchanged. Modify t_band t_nin a similar way. Iteratively modify (t_a, t_b, and t_n) until C can no longer be reduced.

Train Classifiers

Once the classifier sequence is known, thedialog manager106 hierarchically trains each of the

classifiers

116,118, and120 using the set of ground-truth data. For example, if gender classification is performed on the contact's104 dialog before accent classification, then accent classification is trained twice, once on male gender data, and once on female gender data. Also, because downstream classifiers (e.g. accent classification) are only trained on a subset of the ground-truth data, a total training time for all

classifiers

116,118, and120 is shorter than if such downstream classifiers were trained on the complete set of ground-truth data.

Deploy Classifiers

Thedialog manager106 selects a set of resources to effect dialog classification. Preferably, each instance of the

classifiers

116,118, and120 operate in parallel on separate computational resources. For example, in the previous example, three parallel sets of computational resources are preferably used: one set for gender detection; one set for male gender accent classification; and one set for female gender accent classification. Such resource specialization, enables each classifier instance to process a large number of classification requests in a given time period.

Those skilled in the art recognize that a variety of resource selections are possible, including effecting all

classifiers

116,118, and120 on a single computer.

Contact Attribute Extraction From the Dialog

The following discussion assumes that thesequencer122 hierarchically sequenced the classifiers such that thefirst classifier116 is first in the sequence, thesecond classifier118 is second in the sequence, and so on through the (n)thclassifier120 that is (n)th in the sequence.

Thefirst classifier116 waits for a predetermined time for a first length (t_a) of the dialog. The first classifier116 (e.g. gender classifier) assigns the contact to a first attribute category (e.g. male gender) by processing the first length of the dialog. Thedialog manager106 transmits the first attribute category to anysystem102 applications requiring knowledge of the first attribute category.

A first instance of the second classifier118 (e.g. an accent classifier trained on male gender ground-truth data only) waits for a predetermined time for a second length (t_b) of the dialog. The first instance of thesecond classifier118 assigns thecontact104 to a second attribute category (e.g. British Accent) by processing the second length of the dialog. The first instance of thesecond classifier118 is trained to categorize dialogs assigned only to the first attribute category (e.g. contacts identified by thefirst classifier116 as being of male gender). Preferably, the previous step is performed only if the first attribute category has an error probability less than a predetermined value.

If the first attribute category has an error probability greater than a predetermined value, each other instance of the second classifier118 (e.g. such as an accent classifier trained on female gender ground-truth data only) assigns thecontact104 to a second attribute category by processing the second length of the dialog. The other instances of thesecond classifier118 are individually trained to categorize dialogs assigned to other attribute categories that could have been assigned by the first classifier116 (e.g. female gender category). Thesecond classifier118 averages each of the probabilities generated by the other instances of thesecond classifier118 yielding a set of combined second attribute category scores. Thesecond classifier118 assigns to thecontact104 that second attribute category having a highest combined second attribute category score.

Thedialog manager106 transmits the attribute category assigned by thesecond classifier118 to anysystem102 applications requiring knowledge of that attribute category.

A first instance of the (n)th classifier120 (e.g. an age classifier trained only on male gender American accent ground-truth data only) waits for a predetermined time for an (n)th length (t_n) of the dialog. The first instance of the (n)thclassifier120 assigns the contact to an (n)th attribute category (e.g. age attributes) by processing the (n)th length of the dialog. The first instance of the (n)thclassifier120 trained to categorize dialogs assigned only to a predetermined set of attribute categories (e.g. contacts identified by thefirst classifier116 as being of male gender, identified by thesecond classifier118 as having an American accent, and so on) respectively assigned by the first classifier through an (n-1)th classifier. Preferably, the previous step is performed only if the predetermined set of attribute categories all have error probabilities less than a predetermined set of values.

If, however, one or more of the attribute categories has an error probability greater than its respective predetermined value, then other instances of the (n)thclassifier120 assign thecontact104 to other (n)th attribute categories by processing the (n)th length of the dialog. The other instances of the (n)thclassifier120 are trained to categorize dialogs assigned to other first through (n-1)th attribute categories that could have been assigned by the first through (n-1)th classifiers. The (n)thclassifier120 averages each of the probabilities generated by the other instances of (n)thclassifier120 yielding a set of combined (n)th attribute category scores. The (n)thclassifier120 assigns to thecontact104 that (n)th attribute category having a highest combined (n)th attribute category score.

Thedialog manager106 transmits the (n)th attribute category assigned by the (n)thclassifier120 to anysystem102 applications requiring knowledge of that attribute category.

Thus in some instances of the present invention, more than one downstream node can be invoked. For example, the gender classifier may not be very confident about its attribute classification (e.g. a probability of 0.6 as male and 0.4 as female). As a result, both the male and female portions of accent classification are invoked in parallel, and a final accent classification result is a weighted sum of the two individual accent classifications.

These techniques are also applicable to other voice-based sub-classification or sequential classification systems. Temporally-Non-overlapping and Sequential Sub-classification can be applied if there is no overlap in time, and Temporally-Overlapping, Asymptotic-Prediction Limited Parallel Sub-classification can be applied if, multiple sets of computational resources are used, or there are multiple copies of OS on the same machine for in parallel classification (with overlap, but “shutting off” each classifier as it reaches its predicted saturation or accuracy).

FIG. 4 is a root flowchart of one embodiment of amethod400 for hierarchical attribute extraction within a call handling system. Instep402, a dialog between a contact and a call handling system is initiated. Instep404, a first instance of thefirst classifier116 waits for a first length of the dialog. Instep406, the first instance of thefirst classifier116 assigns the contact to a first attribute category by processing the first length of the dialog. Instep408, a first instance of thesecond classifier118 waits for a second length of the dialog. Then instep410, the first instance of thesecond classifier118 assigns the contact to a second attribute category by processing the second length of the dialog. The first instance of thesecond classifier118 is trained to categorize dialogs assigned only to the first attribute category. Theroot method400 is discussed in further detail with respect toFIG. 5.

FIG. 5 is a flowchart of one embodiment of amethod500 for hierarchical attribute extraction within a call handling system. To begin, instep502, acontact104 enters into a dialog with thecall handling system102.

Identify Contact Attributes for Classification

Instep504, thedialog manager106 retrieves a request to identify a set of contact attributes with respect to thecontact104.

Classifier Selection

Instep506, a set of

classifiers

Hierarchically Sequence Classifiers

Instep508, theclassifier sequencer122 sends the ground-truth data to each classifier for classification. In step510, theclassifier sequencer122 receives a set of classification data-points back from each classifier (e.g. a gender classifier and an accent classifier).

Classifier Clustering Characteristics

Instep512, theclassifier sequencer122 calculates an “inter-class distance” between all data-points known (via the ground-truth data) to be within a first attribute category (e.g. “Male Gender”202, or “British Accent”204) and all data-point known to be within a second attribute category (i.e. “Female Gender”206, or “American Accent”208).

Instep514, theclassifier sequencer122 averages all of these inter-class distances over the entire set of classification data-points. Instep516, theclassifier sequencer122 calculates an “intra-class distance” between all data-points known (via the ground-truth data) to be within a first attribute category (e.g. “Male Gender”202, “British Accent”204, “Female Gender”206, or “American Accent”208).

Instep518, theclassifier sequencer122 averages all of these intra-class distances over the entire set of classification data-points.

Next instep520, theclassifier sequencer122 defines a clustering characteristic for each classifier based on a ratio between the average “inter-class distance” and average “intra-class distance”. In step522, theclassifier sequencer122 sequences the

classifiers

116,118, and120 based on this ratio.

Classifier Accuracy Characteristics

Instep524, theclassifier sequencer122 calculates an accuracy rate, which is a ratio between a number of the classification data-points that fall within a correct classifier category, according to the ground-truth data, and a total number of the classification data-points.

Instep526, theclassifier sequencer122 sequences the

classifiers

116,118, and120 based on this accuracy rate.

Classifier Saturation Characteristics

Instep528, theclassifier sequencer122 sends a set of ground-truth data, having a predetermined speech signal or textual length, to each classifier for classification. Instep530, theclassifier sequencer122 receives a set of classification data-points back from each classifier for each of the predetermined speech signal or textual lengths. Instep532, theclassifier sequencer122 calculates an accuracy rate, which is a ratio between a number of the classification data-points that fall within a correct classifier category, according to the ground-truth data, and a total number of the classification data-points, for each of the predetermined speech signal or textual lengths.

Then instep534, theclassifier sequencer122 compares the accuracy rate to the predetermined speech signal or textual lengths, resulting in a classifier saturation curve for each classifier. Instep536, theclassifier sequencer122 sequences the

classifiers

116,118, and120 according to how quickly each classifier reaches a predetermined point in that classifier's saturation curve.

Other Classifier Characteristics

Then instep538, theclassifier sequencer122 stores the classifier characterization data in aclassifier database124.

Classifier Sequencing

Instep540, theclassifier sequencer122 select a sequence for executing each of the

classifiers

116,118, and120 based on a weighted combination of each of the classifier characteristics. Next instep542, theclassifier sequencer122 further optimizes the sequence for executing each of the

classifiers

116,118, and120 using a genetic algorithm.

Optimize Dialog Length Processed by Each Classifier

Instep544, thedialog manager106 selects a dialog length (t_a, t_b, and t_n, respectively) for each of the

classifiers

116,118, and120.

Train Classifiers

classifiers

116,118, and120 using the set of ground-truth data, instep546.

Deploy Classifiers

Instep548, thedialog manager106 selects a set of resources to effect dialog classification.

Contact Attribute Extraction From the Dialog

Instep550, thefirst classifier116 waits for a predetermined time for a first length (t_a) of the dialog. Instep552, the first classifier116 (e.g. gender classifier) assigns the contact to a first attribute category (e.g. male gender) by processing the first length of the dialog. Instep554 thedialog manager106 transmits the first attribute category to anysystem102 applications requiring knowledge of the first attribute category.

Instep556, a first instance of the second classifier118 (e.g. an accent classifier trained on male gender ground-truth data only) waits for a predetermined time for a second length (t_b) of the dialog. Instep558, the first instance of thesecond classifier118 assigns thecontact104 to a second attribute category (e.g. British Accent) by processing the second length of the dialog.

Instep560, if the first attribute category has an error probability greater than a predetermined value, each other instance of the second classifier118 (e.g. including for instance an accent classifier trained on female gender ground-truth data only) assigns thecontact104 to a second attribute category by processing the second length of the dialog.

Instep562, thesecond classifier118 averages each of the probabilities generated by the other instances of thesecond classifier118 yielding a set of combined second attribute category scores. Instep564, thesecond classifier118 assigns to thecontact104 that second attribute category having a highest combined second attribute category score.

Instep566, thedialog manager106 transmits the attribute category assigned by thesecond classifier118 to anysystem102 applications requiring knowledge of that attribute category.

Instep568, a first instance of the (n)th classifier120 (e.g. an age classifier trained only on male gender American accent ground-truth data only) waits for a predetermined time for an (n)th length (t_n) of the dialog. Instep570, the first instance of the (n)thclassifier120 assigns the contact to an (n)th attribute category (e.g. age attributes) by processing the (n)th length of the dialog.

Instep572, if, however, one or more of the attribute categories has an error probability greater than its respective predetermined value, then other instances of the (n)thclassifier120 assign thecontact104 to other (n)th attribute categories by processing the (n)th length of the dialog.

Instep574, the (n)thclassifier120 averages each of the probabilities generated by the other instances of (n)thclassifier120 yielding a set of combined (n)th attribute category scores. Instep576, the (n)thclassifier120 assigns to thecontact104 that (n)th attribute category having a highest combined (n)th attribute category score.

Instep578, thedialog manager106 transmits the (n)th attribute category assigned by the (n)thclassifier120 to anysystem102 applications requiring knowledge of that attribute category.

While one or more embodiments of the present invention have been described, those skilled in the art will recognize that various modifications may be made. Variations upon and modifications to these embodiments are provided by the present invention, which is limited only by the following claims.

Claims

1. A method for hierarchical attribute extraction, comprising:

initiating a dialog between a contact and a call handling system;

waiting for a first length of the dialog;

assigning the contact to a first attribute category by processing the first length of the dialog using a first instance of a first classifier;

waiting for a second length of the dialog; and

assigning the contact to a second attribute category by processing the second length of the dialog using a first instance of a second classifier trained to categorize dialogs assigned only to the first attribute category.

2. The method ofclaim 1, wherein:

the first attribute category is a gender category; and

the second attribute category is an accent category.

3. The method ofclaim 1, further comprising:

transmitting the first attribute category to an application hosted by the call handling system before assigning the second attribute category.

4. The method ofclaim 1, further comprising:

processing the second length of the dialog using other instances of the second classifier trained to categorize dialogs assigned to other attribute categories that could have been assigned by the first classifier, if the first attribute category has an error probability greater than a predetermined value;

averaging a set of probabilities generated by each instance of the second classifier yielding a set of combined second attribute category scores; and

assigning the contact to that second attribute category having a highest combined second attribute category score.

5. The method ofclaim 1, further comprising:

waiting for an (n)th length of the dialog; and

assigning the contact to an (n)th attribute category by processing the (n)th length of the dialog using an (n)th classifier trained to categorize dialogs assigned only to a predetermined set of attribute categories respectively assigned by the first through (n-1)th classifiers.

6. The method ofclaim 5, further comprising:

processing the (n)th length of the dialog using other (n)th classifiers trained to categorize dialogs assigned to either the predetermined set of attribute categories or another set of attribute categories that could have been assigned by the first through (n-1)th classifiers, if one of the attribute categories has an error probability greater than a predetermined value;

averaging a set of probabilities generated by each instance of (n)th classifier yielding a set of combined (n)th attribute category scores; and

assigning the contact to that (n)th attribute category having a highest combined (n)th attribute category score.

7. The method ofclaim 1, wherein:

the dialog includes textual messages.

8. The method ofclaim 1, further comprising:

selecting the first classifier and the second classifier based on a weighted combination of each classifier's characteristics.

9. The method ofclaim 8, further comprising:

generating a set of attribute category data-points using a classifier;

defining an inter-class distance as a distance between a first data-point within an attribute category and a second data-point within another attribute category;

defining an intra-class distance as a distance between the first data-point and a third data-point within the attribute category;

comparing the inter-class distance with the intra-class distance; and

assigning a clustering characteristic to the classifier based on the comparison.

10. The method ofclaim 8, further comprising:

generating a set of attribute category data-points using a classifier;

comparing a number of the data-points that fall within a correct contact attribute category to a total number of data-points within the set of attribute category data-points; and

assigning an accuracy characteristic to the classifier based on the comparison.

11. The method ofclaim 8, further comprising:

generating a first error probability from a classifier that processes a first pre-set dialog length;

generating a second error probability from the classifier that processes a second pre-set dialog length;

comparing the first and second error probabilities; and

assigning a saturation characteristic to the classifier based on the comparison.

12. The method ofclaim 8, further comprising:

assigning a resource requirement characteristic to each classifier.

13. The method ofclaim 8, further comprising:

assigning a cost characteristic to each classifier.

14. A computer-usable medium embodying program code for commanding a computer to effect hierarchical attribute extraction, comprising:

initiating a dialog between a contact and a call handling system;

waiting for a first length of the dialog;

waiting for a second length of the dialog; and

15. The medium ofclaim 14, further comprising:

16. The medium ofclaim 14, further comprising:

waiting for an (n)th length of the dialog; and

assigning the contact to an (n)th attribute category by processing the (n)th length of the dialog using an (n)th classifier trained to categorize dialogs assigned only to a predetermined set of attribute catergories respectively assigned by the first through (n-1)th classifiers.

17. The medium ofclaim 16, further comprising:

18. A system for hierarchical attribute extraction, comprising a:

means for initiating a dialog between a contact and a call handling system;

means for waiting for a first length of the dialog;

means for assigning the contact to a first attribute category by processing the first length of the dialog using a first instance of a first classifier;

means for waiting for a second length of the dialog; and

means for assigning the contact to a second attribute category by processing the second length of the dialog using a first instance of a second classifier trained to categorize dialogs assigned only to the first attribute category.

19. The system ofclaim 18, further comprising:

means for processing the second length of the dialog using other instances of the second classifier trained to categorize dialogs assigned to other attribute categories that could have been assigned by the first classifier, if the first attribute category has an error probability greater than a predetermined value;

means for averaging a set of probabilities generated by each instance of the second classifier yielding a set of combined second attribute category scores; and

means for assigning the contact to that second attribute category having a highest combined second attribute category score.

20. The system ofclaim 18, further comprising:

means for selecting the first classifier and the second classifier based on a weighted combination of each classifier's characteristics.